Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    how and where questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    장은
    0.41
    博客
    0.41
     noemen
    0.41
     داش
    0.40
     జాగ్ర
    0.39
    ài
    0.39
    وڑا
    0.39
    זור
    0.39
    интере
    0.38
    dden
    0.38
    POSITIVE LOGITS
     IMC
    0.42
     puri
    0.42
     Nm
    0.41
     contraceptives
    0.39
    احث
    0.39
     pianos
    0.37
     coiled
    0.37
     Lupus
    0.37
     catheters
    0.37
     MU
    0.37
    Act Density 0.001%

    No Known Activations